Comparing different methods of estimation for Probability of Informed Trading in Tehran Stock Exchange

Easley and O'Hara (1992) introduce Probability of Informed Trading (PIN) concept to measure the degree of asymmetric information in market. Since then there has been a lot of debate on the accuracy of the calculations for PIN. Lin and Ke (2011) by using Factorization method and Yan and Zhang (2012) using Grid-Search based methods introduced other ways to improve the accuracy of the measurement. In this paper, we compare four different methods of PIN calculation for 206 selected companies for listed companies in Tehran Stock Exchange (TSE). We used maximum likelihood method to estimate parameters. The results show that the average of PIN for LK methodology is 0.242 and for EHO is 0.281 in our sample. Moreover, clustering Approach is faster which make it more suitable for practical applications in the real market. Comparison of standard deviation of different methods shows that Grid Search approach is more stable with lower variations in the results.